22
Automating Enterprise Business Processes using AI Naghi Prasad Xu Miao

Naghi Prasad at AI Frontiers: Building AI systems to automate enterprise process flows

Embed Size (px)

Citation preview

Automating Enterprise Business Processes using AI

Naghi PrasadXu Miao

22

AI-driven enterprise applications

•Business processes mapped to an AI engine to enable business efficiencies.

•4 business processes being automated by AI Customer Support

Recruiting

Content Marketing

AdTech

• We will conclude with lessons learned from being very involved in these companies since inception.

33

But then what is AI? – Lessons Learned

•AI is a rich source of interesting toolsLot more than Deep Learning, CNN, Generative Adversarial

Networks!!

Suite of techniques to evoke intelligence : Categorizers, Regression, NLP, Case-Based reasoning etc.

•Domain driven rather than technique drivenLet the domain drive the problem solving and which techniques

you use from the bag

•Interesting Data strategies

•AI application is like a raisin bread : it is still 90% bread

4

NevaAI-Driven Automation for Service and Support

55

Why Neva?

Customer service organizations must improve support quality while reducing delivery costs.

Key challenges

Fragmented knowledge from disparate knowledge sources and

enterprise systems, and decentralized change management.

Inefficient decision-making due to gap between front and back

office, frequent changes, and inability to continuously train human

agents.

Fractured user experience due to omni-channel, modern support

outside work and inefficient, human-based support at work

77

Structured

Complicated Data Environment

Structured

Operational DBs

Datawarehouse

APsEnterprise APIs

StructuredUnstructured

Knowledge Articles

Forum Posts

Screen shots

StructuredSemi-structured

E-mails

Log/message history

8

Model Driven Intelligent Data Process

Search GraphMySQL RedisHive/Presto

Active Learning

Input Query analysis

Knowledge

Releva

nce

Indexing

Ranking

BusinessLogic

Document understanding

output

Inference Learning

SQL

OLTP OLAP

SkitLearn

www.swooptalent.com

Talent Data Cloud with SwoopTalent

www.swooptalent.com

Your PRIVATE data backbone

Data from ALL sources matched & made available

Private Talent Data Cloud

Production ATS - cloud

Data from prior ATS

CRM and other live systems -

cloud

Hundreds of millions of social talent records gathered by Swoop

Resumes, Spreadsheets,

etc

www.swooptalent.com

Candidate Profiles on SwoopTalent

External (public) records

Combined data: rich, fresh, searchable, analyzableInternal ATS records

www.swooptalent.com

Swoop AI Layer

More Structured Less Structured

ATS, CRMXML, Excel, Flat

Files,Social Media, Niche

Forums, Society BoardsDocs, PDF, JPG,

Supervised Learning

TokenizationPart of Speech

Named Entity Recognition

Custom Pipelines

Unsupervised Learning

Clustering Similarity

Latent Semantic Analysis, SVD, Word2Vec

Topic Modeling (160 Million Profiles)

Data Data

Data Data

Search

Semantic Query

Processing

Topic Modeling

Application

Up IQAutonomous MarketingTM

Copyright 2016 Confidential & Proprietary | Not Meant for Distribution

Automatically generates statistically relevant marketing content that is highly personalized

10x better conversion rates for organic search

Enterprises Journey to Autonomous Marketing

Data

Sync

Banks Data

Social Data

Public Records

Data

Cleansing

Data is Engineered

Content

Creation

Search Content

Social Content

Email & Text

Machine

Learning

NLPK

Data Science

• Markovian Modeling

Up IQ to Power Banks: SEM Campaigns, & Landing Pages

Customers Journey, from Discovery to Acquisition

Personalized

Banks

Retail Banks

Mortgage Banks

Online Lenders

Relevant

Bank Staff

Ranked Bank Staff

Content

Discovery

Search Content

Social Content

Email & Text

• Information Theoretic Scoring• Sentiment Analysis

Deep Forest Mediaa Rakuten Company

Cross Device Graph

1919

Machine learning models device graph relationships : naive Bayes modeling &heuristics for pruning.

172.0.0.217Feature engineering (UID, IP, user agent, referral url, login email etc.)

Data Collection (cookie-sync, exchanges, ad impression, native sdk, 3rd party data

Identify users across smartphones, tablets & desktops

Bid Price Optimization

20

• A dynamic pricing algorithm

– maximizes the expected value of gain after winning an auction, or 𝑏 =𝑎𝑟𝑔𝑚𝑎𝑥𝑏 𝐸 𝑔𝑎𝑖𝑛

– adjusts automatically to meet business requirements (ex. CPM margin) using a feedback loop

auction data

user data

win rate

win price

purchase prediction

ctr

bidding strategy

bid price

business requirements

alpha

• Machine learning modelswin rate – binary classification (Random forest)win price – regressionpurchase prediction – binary classification

(Random forest)CTR – binary classification

2121

But then what is AI? – Lessons Learned

•AI is a rich source of toolsDeep Learning, CNN, Generative Adversarial Networks

Categorizers, Regression, NLP, Case-Based reasoning etc.

•Domain driven rather than technique driven

•Interesting Data strategies

•AI application is like a raisin bread : it is still 90% bread